Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Hongru, Kailkhura, Bhavya, Wang, Zhangyang, Liang, Yingbin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!